asm_parser.py

#!/usr/bin/env python3

from pyparsing import Word, hexnums, WordEnd, Optional, alphas, alphanums
from multiprocessing import Pool
import pandas as pd 
import re
import os
import sys

class asm_cruncher:

	def dll_finder(self,filename):
		dll_list = {};
		dll_list['file'] = filename
		rex = '[A-Za-z0-9]*\.dll'
		with open(filename,"r",encoding="ISO-8859-1")as source:
			for line in source:
				try:
					x = re.search(rex,line,re.I).group(0).strip().lower()
					if x in dll_list.keys():
						dll_list[x] = dll_list[x] + 1
					else:
						dll_list[x] = 1			
				except Exception as e:
					pass
		return dll_list			

	def section_finder(self,filename):
		sec_list = {}
		sec_list['file'] = filename

		with open(filename,"r", encoding = "ISO-8859-1")as source:
			for line in source:
				if line[0] == "." or line[0] == 'H':
					x = line[:line.find(":")].lower()
					if x in sec_list.keys():
						sec_list[x] = sec_list[x] + 1
					else:
						sec_list[x] = 1
		return sec_list				

	def opcode_finder(self,filename):
		opcode_list = {}
		opcode_list['file'] = filename

		hex_integer = Word(hexnums) + WordEnd() # use WordEnd to avoid parsing leading a-f of non-hex numbers as a hex
		line = hex_integer + Optional((hex_integer*(1,))("instructions") + Word(alphas,alphanums)("opcode"))

		with open(filename,"r", encoding = "ISO-8859-1")as source:
			for source_line in source:
				if source_line[0] == '.':
					try:
						x = source_line[:source_line.find(":")+1]+line
						result = x.parseString(source_line)
						if "opcode" in result and not bool(re.match(r'[A-F0-9][A-F0-9]',result.opcode)):
							if result.opcode in opcode_list.keys():
								opcode_list[result.opcode] = opcode_list[result.opcode] + 1
							else:
								opcode_list[result.opcode] = 1

					except Exception as e:
						raise e					
		return opcode_list				


if __name__ == '__main__':
	proc = int(sys.argv[1])
	obj = asm_cruncher()
	res_list = {'dll_data.csv':obj.dll_finder, 'section_data.csv':obj.section_finder, 'opcode_data.csv':obj.opcode_finder}			
	o_path = os.getcwd()
	for item in res_list.keys():
		os.chdir(os.path.join(os.getcwd(), "Dataset", "asm"))
		filelist = [x for x in os.listdir() if ".asm" in x]		
		with Pool(proc) as p:
			df = p.map(res_list[item], filelist)
		os.chdir(o_path)	
		frame = pd.DataFrame(df)
		frame = frame.set_index('file')
		pd.options.display.float_format = '{:.0f}'.format
		print(frame, "\n")
		frame.to_csv(os.path.join("results",item), sep = ',', encoding = 'utf-8', index = True, float_format="%.0f")